The fastest inference engine for agents and streams.

Real-time data breaks every inference engine. We built LayerScale that stays fast no matter how much data you throw at it.

Accelerated by
Metal API COMPATIBLE API COMPATIBLE Metal API COMPATIBLE API COMPATIBLE
33ms
Average query latency
8x
Faster than vLLM and SGLang
O(1)
Query complexity
80x
Faster than Claude Opus 4.5

Rethinking inference.
Process the stream, not the request.

LayerScale introduces a new computation model. Data is processed the moment it arrives, not when you query. By the time you ask a question, the answer is already there.

01

Data-Driven Processing

Data flows continuously into the cache. Processing happens in the background, amortized across your data stream. Queries become lightweight consumers of pre-computed state.

02

Constant Query Latency

Query latency depends on your question length, not your context size. Whether you have 100 data points or 10,000, query time stays the same.

03

Full Attention Preserved

Unlike sparse attention or state-space models that sacrifice model capacity for speed, LayerScale maintains full quadratic self-attention. No quality compromises.

8x Faster Than Leading
Inference Engines

LayerScale
33ms
SGLang
219ms 7x
vLLM
223ms 7x
TensorRT-LLM
255ms 8x
llama.cpp
261ms 8x
GPT-5.2
926ms 28x
GPT-4o
1,124ms 34x
Opus 4.5
2,628ms 80x
Local inference Cloud API

Benchmarked on streaming OHLCV data (155 to 1,200 samples, ~2,600 to 19,000 tokens). Local engines use Meta-Llama-3.1-8B-Instruct on NVIDIA L40S GPU. Cloud APIs called via their respective endpoints.

Fastest Inference Engine
for Agentic AI

AI agents call tools dozens of times per task. Every call forces conventional engines to re-process the full conversation from scratch. LayerScale persists prior computation across calls, so each agent's state stays resident on the GPU. The result: constant latency no matter how deep the conversation gets.

LayerScale SGLang TensorRT-LLM vLLM llama.cpp

Per-call latency across 45 interleaved multi-agent tool calls (3 iterations × 3 agents × 5 turns), Llama-3.1-8B-Instruct on NVIDIA L40S GPU. LayerScale maintains constant 66ms latency while llama.cpp climbs from 89ms to 130ms as context grows.

Built for Streaming
from the Ground Up

LayerScale manages context through intelligent regions so each data pattern gets the right treatment. A lock-free ingestion pipeline ensures data pushes never block. O(1) tokenization via pre-computed lookup tables eliminates overhead on the critical path, and fast-path detection returns single-token classification answers immediately.

Conventional
Query
Full ReprocessO(n)
Response
vs
LayerScale
Data Stream
Pre-computed Cachealways-on
Query
ResponseO(1)

Where LayerScale Excels

Market Data

Real-time analysis over continuous OHLCV feeds with sub-50ms responses.

Log Analysis

Stream logs continuously and query for anomalies without reprocessing.

Sensor Monitoring

IoT data processed in real-time with instant analytical queries.

Real-Time Analytics

Instant answers over accumulated context as data streams in.

Run Any Model
on Any Hardware

Any open-weight transformer model, optimized and production-ready across all major accelerator platforms.

Open Models
Meta Llama 4
Google Gemma 3
DeepSeek DeepSeek V3.2
Mistral AI Mistral Large 3
Qwen Qwen 3
Microsoft Phi-4
NVIDIA Nemotron 3
+ More Any open-weight transformer
Hardware Platforms
NVIDIA CUDA RTX 20xx+, T4, L40S, A10, A100, H100, B200, B300
AMD ROCm Instinct MI250, MI300X, MI455X
Intel Arc Arc A-Series, Data Center GPU Max
Apple Metal M1, M2, M3, M4, M5 Pro / Max / Ultra

Anthropic/OpenAI Compatible API

Drop-in replacement for existing workflows. Standard endpoints with streaming support, plus specialized session APIs for continuous data injection. Python and TypeScript client libraries available.

Endpoints

  • POST /v1/chat/completions OpenAI-compatible
  • POST /v1/messages Anthropic-compatible
  • POST /v1/sessions/init Create session
  • POST /v1/sessions/{id}/stream/push Push data
  • POST /v1/sessions/{id}/generate O(1) query
  • GET /v1/sessions/{id}/stream/status Stream stats

Streaming endpoints also available via WebSockets, TCP sockets, and Server-Sent Events (SSE) for low-latency persistent connections.

terminal
# Initialize a streaming session
curl -X POST https://api.layerscale.ai/v1/sessions/init \
  -H "Content-Type: application/json" \
  -d '{"prompt": "You are a financial analyst..."}'

# Push streaming data (non-blocking)
curl -X POST https://api.layerscale.ai/v1/sessions/{id}/stream/push \
  -H "Content-Type: application/json" \
  -d '{"data": [{"o": 150.25, "h": 151.00, "l": 149.80, "c": 150.90, "v": 100000}]}'

# Query with constant latency
curl -X POST https://api.layerscale.ai/v1/sessions/{id}/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt": "What is the current trend?"}'

Flash Queries

Define your questions upfront and get pre-computed answers after every data update, streamed back via SSE with zero GPU work. Learn more →

Run Anywhere

Docker Recommended

docker run --gpus all \
  -v /models:/models -p 8080:8080 \
  layerscale-server:latest \
  --model /models/your-model

Cloud API

# Use the hosted API directly
curl -X POST https://api.layerscale.ai/v1/sessions/init \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "You are a financial analyst..."}'

GPU Support

NVIDIA T4, RTX 20xx+, L4, L40S, A10, A100, H100, B200, B300, MI455X. Supports CUDA, ROCm, and Metal.

Model Support

Any open-weight model. Llama, Mistral, Qwen, Gemma, and more work out of the box.

Platforms

Linux recommended for production. macOS supported for development.

Frequently Asked Questions

Virtually any open-weight transformer model. Popular models like Llama, Mistral, Qwen, and Gemma work out of the box, with automatic format conversion included.
Those are request-driven frameworks optimized for serving many users with shared prefixes. LayerScale is data-driven, optimized for streaming scenarios where context changes continuously and queries need instant answers.
LayerScale works fine for chat applications, but provides no benefit over conventional inference engines in that scenario. If you don't have continuous data ingestion, a conventional inference engine is probably a better fit.
Yes. We support the Anthropic /v1/messages endpoint and the OpenAI /v1/chat/completions endpoint. Just point your existing client to the LayerScale API.
Each session maintains cache proportional to context length. We implement session pooling and LRU eviction for multi-session deployments. Bounded memory with configurable sliding windows keeps resource usage predictable.